| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010814708002883922, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003604902667627974, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.5685, | |
| "eval_samples_per_second": 70.555, | |
| "eval_steps_per_second": 35.308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010814708002883922, | |
| "grad_norm": 1.230961879628012e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001802451333813987, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 17.403, | |
| "eval_samples_per_second": 67.172, | |
| "eval_steps_per_second": 33.615, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021629416005767843, | |
| "grad_norm": 1.573328881931957e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032444124008651765, | |
| "grad_norm": 1.3633475646201987e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003604902667627974, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.8716, | |
| "eval_samples_per_second": 69.288, | |
| "eval_steps_per_second": 34.674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004325883201153569, | |
| "grad_norm": 1.2278750546101946e-05, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005407354001441961, | |
| "grad_norm": 1.0704851774789859e-05, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005407354001441961, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.5777, | |
| "eval_samples_per_second": 70.517, | |
| "eval_steps_per_second": 35.288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006488824801730353, | |
| "grad_norm": 2.0603651137207635e-05, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007209805335255948, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.9564, | |
| "eval_samples_per_second": 68.942, | |
| "eval_steps_per_second": 34.5, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007570295602018745, | |
| "grad_norm": 1.9149787476635538e-05, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008651766402307137, | |
| "grad_norm": 2.979295823024586e-05, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009012256669069935, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.6576, | |
| "eval_samples_per_second": 70.178, | |
| "eval_steps_per_second": 35.119, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00973323720259553, | |
| "grad_norm": 1.7904030755744316e-05, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010814708002883922, | |
| "grad_norm": 2.0520408725133166e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010814708002883922, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 16.9066, | |
| "eval_samples_per_second": 69.145, | |
| "eval_steps_per_second": 34.602, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1954908340224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |